Commit e2661da1 authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge tag 'io_uring-6.15-20250515' of git://git.kernel.dk/linux 

Pull io_uring fixes from Jens Axboe:

 - Fix a regression with highmem and mapping of regions, where
   the coalescing code assumes any page is directly mapped

 - Fix an issue with HYBRID_IOPOLL and passthrough commands,
   where the timer wasn't always setup correctly

 - Fix an issue with fdinfo not correctly locking around reading
   the rings, which can be an issue if the ring is being resized
   at the same time

* tag 'io_uring-6.15-20250515' of git://git.kernel.dk/linux:
  io_uring/fdinfo: grab ctx->uring_lock around io_uring_show_fdinfo()
  io_uring/memmap: don't use page_address() on a highmem page
  io_uring/uring_cmd: fix hybrid polling initialization issue
parents 1524cb28 d871198e

io_uring/fdinfo.c

+25 −23
Original line number Diff line number Diff line
@@ -86,13 +86,8 @@ static inline void napi_show_fdinfo(struct io_ring_ctx *ctx, 
}

#endif



/*

 * Caller holds a reference to the file already, we don't need to do

 * anything else to get an extra reference.

 */

__cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file)

static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m)

{

	struct io_ring_ctx *ctx = file->private_data;

	struct io_overflow_cqe *ocqe;

	struct io_rings *r = ctx->rings;

	struct rusage sq_usage;
@@ -106,7 +101,6 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file) 
	unsigned int sq_entries, cq_entries;

	int sq_pid = -1, sq_cpu = -1;

	u64 sq_total_time = 0, sq_work_time = 0;

	bool has_lock;

	unsigned int i;



	if (ctx->flags & IORING_SETUP_CQE32)
@@ -176,15 +170,7 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file) 
		seq_printf(m, "\n");

	}



	/*

	 * Avoid ABBA deadlock between the seq lock and the io_uring mutex,

	 * since fdinfo case grabs it in the opposite direction of normal use

	 * cases. If we fail to get the lock, we just don't iterate any

	 * structures that could be going away outside the io_uring mutex.

	 */

	has_lock = mutex_trylock(&ctx->uring_lock);



	if (has_lock && (ctx->flags & IORING_SETUP_SQPOLL)) {

	if (ctx->flags & IORING_SETUP_SQPOLL) {

		struct io_sq_data *sq = ctx->sq_data;



		/*
@@ -206,7 +192,7 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file) 
	seq_printf(m, "SqTotalTime:\t%llu\n", sq_total_time);

	seq_printf(m, "SqWorkTime:\t%llu\n", sq_work_time);

	seq_printf(m, "UserFiles:\t%u\n", ctx->file_table.data.nr);

	for (i = 0; has_lock && i < ctx->file_table.data.nr; i++) {

	for (i = 0; i < ctx->file_table.data.nr; i++) {

		struct file *f = NULL;



		if (ctx->file_table.data.nodes[i])
@@ -218,7 +204,7 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file) 
		}

	}

	seq_printf(m, "UserBufs:\t%u\n", ctx->buf_table.nr);

	for (i = 0; has_lock && i < ctx->buf_table.nr; i++) {

	for (i = 0; i < ctx->buf_table.nr; i++) {

		struct io_mapped_ubuf *buf = NULL;



		if (ctx->buf_table.nodes[i])
@@ -228,7 +214,7 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file) 
		else

			seq_printf(m, "%5u: <none>\n", i);

	}

	if (has_lock && !xa_empty(&ctx->personalities)) {

	if (!xa_empty(&ctx->personalities)) {

		unsigned long index;

		const struct cred *cred;
@@ -238,7 +224,7 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file) 
	}



	seq_puts(m, "PollList:\n");

	for (i = 0; has_lock && i < (1U << ctx->cancel_table.hash_bits); i++) {

	for (i = 0; i < (1U << ctx->cancel_table.hash_bits); i++) {

		struct io_hash_bucket *hb = &ctx->cancel_table.hbs[i];

		struct io_kiocb *req;
@@ -247,9 +233,6 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file) 
					task_work_pending(req->tctx->task));

	}



	if (has_lock)

		mutex_unlock(&ctx->uring_lock);



	seq_puts(m, "CqOverflowList:\n");

	spin_lock(&ctx->completion_lock);

	list_for_each_entry(ocqe, &ctx->cq_overflow_list, list) {
@@ -262,4 +245,23 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file) 
	spin_unlock(&ctx->completion_lock);

	napi_show_fdinfo(ctx, m);

}



/*

 * Caller holds a reference to the file already, we don't need to do

 * anything else to get an extra reference.

 */

__cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file)

{

	struct io_ring_ctx *ctx = file->private_data;



	/*

	 * Avoid ABBA deadlock between the seq lock and the io_uring mutex,

	 * since fdinfo case grabs it in the opposite direction of normal use

	 * cases.

	 */

	if (mutex_trylock(&ctx->uring_lock)) {

		__io_uring_show_fdinfo(ctx, m);

		mutex_unlock(&ctx->uring_lock);

	}

}

#endif

io_uring/memmap.c

+1 −1
Original line number Diff line number Diff line
@@ -116,7 +116,7 @@ static int io_region_init_ptr(struct io_mapped_region *mr) 
	void *ptr;



	if (io_check_coalesce_buffer(mr->pages, mr->nr_pages, &ifd)) {

		if (ifd.nr_folios == 1) {

		if (ifd.nr_folios == 1 && !PageHighMem(mr->pages[0])) {

			mr->ptr = page_address(mr->pages[0]);

			return 0;

		}

io_uring/uring_cmd.c

+5 −0
Original line number Diff line number Diff line
@@ -254,6 +254,11 @@ int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags) 
			return -EOPNOTSUPP;

		issue_flags |= IO_URING_F_IOPOLL;

		req->iopoll_completed = 0;

		if (ctx->flags & IORING_SETUP_HYBRID_IOPOLL) {

			/* make sure every req only blocks once */

			req->flags &= ~REQ_F_IOPOLL_STATE;

			req->iopoll_start = ktime_get_ns();

		}

	}



	ret = file->f_op->uring_cmd(ioucmd, issue_flags);